Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific mentions of organizations, such as institutions, companies, and military branches

    oai_token-act-pair · gpt-3.5-turbo

    references to military and royal institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odynam
    -0.80
    venient
    -0.73
    urious
    -0.73
    atically
    -0.71
    natureconservancy
    -0.71
    antically
    -0.71
     flares
    -0.69
    hetically
    -0.68
    itiveness
    -0.66
    urat
    -0.66
    POSITIVE LOGITS
    VPN
    0.74
     Honour
    0.71
     sshd
    0.70
    ãĥ¼ãĥ³
    0.69
     throne
    0.67
     Seym
    0.66
    clave
    0.66
     Taxi
    0.65
     Cortex
    0.64
     Execution
    0.64
    Act Density 0.214%

    No Known Activations